Lever: Inference-Time Policy Reuse under Support Constraints

arXiv:2604.20174v1 Announce Type: new Abstract: Reinforcement learning (RL) policies are typically trained for fixed objectives, making reuse difficult when task requirements change. We study inference-time policy reuse: given a library of pre-trained policies and a new composite objective, can a high-quality policy be constructed entirely offline, without additional environment interaction? We introduce lever (Leveraging Efficient Vector Embeddings for Reusable policies), an end-to-end framework that retrieves relevant policies, evaluates them using behavioral embeddings, and composes new policies via offline Q-value composition. We focus on the support-limited regime, where no value propagation is possible, and show that the effectiveness of reuse depends critically on the coverage of available transitions. To balance performance and computational cost, lever proposes composition strategies that control the exploration of candidate policies. Experiments in deterministic GridWorld environments show that inference-time composition can match, and in some cases exceed, training-from-scratch performance while providing substantial speedups. At the same time, performance degrades when long-horizon dependencies require value propagation, highlighting a fundamental limitation of offline reuse.

Related

• Offline-Online Reinforcement Learning for Linear Mixture MDPs
• A Hessian-Free Actor-Critic Algorithm for Bi-Level Reinforcement Learning with Applications to LLM Fine-Tuning
• Fitted Q Evaluation Without Bellman Completeness via Stationary Weighting
• Wasserstein Formulation of Reinforcement Learning. An Optimal Transport Perspective on Policy Optimization
• A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance
• MDP Planning as Policy Inference

Source: arXiv cs.LG | 2026-04-23